feat: added gear-mesh physics + GearProvider (cross-domain: SEU gearb…

.gitignore

@@ -0,0 +1,220 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+*.lcov
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi/*
+!.pixi/config.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule*
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

EXPERIMENTS.md

@@ -0,0 +1,90 @@
+# Experiments
+A running log of every validation run, benchmark, and cross-domain test for CNSD.
+
+**Discipline for this file** (so it stays a record, not a trophy case):
+- Every entry is tied to a **commit** and a **fixed seed**. The commit's git timestamp is the authoritative date — no manually entered dates.
+- The **run record** (command, commit, environment, config, sample counts) is **auto-generated by the run script** and pasted in verbatim — not transcribed by hand.
+- The experiment and its purpose are stated *before* the result.
+- Null, weak, and unflattering results (abstention rates, accuracy drops, limitations) are recorded alongside the headline numbers.
+- Each entry carries a status: `planned` · `running` · `preliminary` · `validated` · `superseded`.
+
+**How to reproduce any entry**: check out the commit in its run record, prepare the dataset as described in `data/README` (layout + expected sample count / checksum), install the pinned environment (`requirements.txt`), and run the exact command shown in the run record. Numbers should match within run-to-run noise (seeds are fixed; minor GPU nondeterminism is expected).
+
+---
+
+## Index
+
+| # | Experiment | Domain | Status |
+|---|------------|--------|--------|
+| 1 | CWRU baseline (Protocol B) | Bearing (CWRU) | preliminary |
+| 2 | Threshold sweep | Bearing (CWRU) | preliminary |
+| 3 | Cross-condition robustness (AWGN) | Bearing (CWRU) | preliminary |
+| 4 | Multi-seed headline | Bearing (CWRU) | planned |
+| 5 | Cross-domain: SEU gearbox | Gear (SEU) | preliminary (failed) |
+
+---
+
+## 1. CWRU baseline — Protocol B (cross-load)
+
+* **Status:** preliminary
+* **Purpose:** confirm the full five-layer pipeline runs end-to-end on real CWRU and establish the baseline diagnosis result.
+* **Setup:** train loads 0–2, test load 3. All 10 classes. 12 kHz, window 1024.
+
+**Run record**
+```text
+commit:   cd7771ab3668caf9b33109c3a0a9d89f24fd111c
+command:  python validate_run.py --seed 42
+data:     5806 train / 2019 test samples
+```
+
+**Layer-2 physics verification rate**
+| Verdict | Rate |
+|---------|------|
+| CONFIRMED | TBD |
+| CONFLICT | TBD |
+| INCONCLUSIVE | TBD |
+
+**Headline — CNN accuracy by physics verdict**
+| Verdict | n | CNN accuracy |
+|---------|---|--------------|
+| CONFIRMED | TBD | TBD |
+| CONFLICT | TBD | TBD |
+| INCONCLUSIVE | TBD | TBD |
+| **Gap (CONFIRMED - CONFLICT)** | | **TBD** |
+
+* **Causal (Layer 3)** — `do(Z)`: rung *TBD*, max_contrast *TBD*, p *TBD*
+* **Counterfactual (Layer 3B)**: DoWhy available *TBD*; method *TBD*
+* **Notes / limitations**: record the INCONCLUSIVE rate and any seed drift.
+
+---
+
+## 5. Cross-domain — SEU gearbox (GearProvider)
+
+* **Status:** preliminary (failed validation)
+* **Purpose:** demonstrate the framework is genuinely domain-agnostic — same engine, different machine class, only the provider changes.
+* **Setup:** full pipeline on SEU gearset using `GearProvider` (gear-mesh physics). `N_TEETH_INPUT` confirmed against rig spec; fixed channel chosen up front; threshold tuned on a held-out split.
+
+**Run record**
+```text
+commit:   <PENDING PR 12 MERGE>
+command:  python validate_seu.py
+data:     5115 train / 5115 test samples
+n_teeth_input: 20 | channel: 2 (planetary x-axis)
+```
+
+**Layer-2 physics verification rate**
+| Verdict | Rate |
+|---------|------|
+| CONFIRMED | 0.2% |
+| CONFLICT | 0.3% |
+| INCONCLUSIVE | 99.5% |
+
+**Headline — CNN accuracy by physics verdict**
+| Verdict | n | CNN accuracy |
+|---------|---|--------------|
+| CONFIRMED | 9 | 0.333 |
+| CONFLICT | 17 | 0.824 |
+| INCONCLUSIVE | 5089 | 0.514 |
+| **Gap (CONFIRMED - CONFLICT)** | | **-0.491 (FAILED)** |
+
+* **Known caveats to report honestly:** The accuracy gap is currently backwards and practically noise due to a 99.5% inconclusive rate. This is pending a strict `tau` threshold calibration sweep for gear physics, as well as confirming that GMF strength aligns with the same numerical scale as bearing physics.

cnsd/builder.py

@@ -93,6 +93,15 @@ def build_provider(config):
         cond_to_rpm = _coerce_int_keys(params.get('motor_load_rpm', {0: 1797}))
         return provider_cls(bearing=geometry, cond_to_rpm=cond_to_rpm, fs=fs)
 
+    if domain_type == 'gear':
+        cond_to_rpm = _coerce_int_keys(params.get('motor_load_rpm', {0: 1800}))
+        return provider_cls(
+            n_teeth_input=params['n_teeth_input'],
+            n_teeth_output=params.get('n_teeth_output'),
+            cond_to_rpm=cond_to_rpm,
+            fs=fs,
+        )
+
     # other registered domains: pass parameters through + fs
     try:
         return provider_cls(fs=fs, **params)

cnsd/physics/configs.py

@@ -5,9 +5,9 @@
 
 @dataclass
 class PhysicsConfig:
-    bearing: dict[str, float]
     cond_to_rpm: dict
     fs: int
+    bearing: dict[str, float] | None = None
     name: str = 'custom'
 
 
@@ -25,4 +25,9 @@ class PhysicsConfig:
     name='JNU-N205',
 )
 
-SEU_PHYSICS = None
+SEU_PHYSICS = PhysicsConfig(
+    bearing=None,
+    cond_to_rpm={0: 1200, 1: 1800},
+    fs=20000,
+    name='SEU-Gearbox',
+)